🇺🇸 Can watching dialogue across party lines reduce polarisation?
➡️ L-O Ankori-Karlinsky, @robert_a_blair, J. Gottlieb & @smooreberg show that a documentary of an intergroup workshop reduces polarisation and boosts faith in democracy cambridge.org/core/journals/…#FirstView
1st paper from my lab out @CommunicationsPsychology @CommsPsycholnature.com/articles/s4427…
We show an alternative way to understand how people mentally represent other people's characteristics, namely high-dimensional networks, beyond the popular latent factor models.
1st paper from my lab out @CommunicationsPsychology @CommsPsycholnature.com/articles/s4427…
We show an alternative way to understand how people mentally represent other people's characteristics, namely high-dimensional networks, beyond the popular latent factor models.
Currently in FirstView: In “Attention and Political Choice: A Foundation for Eye Tracking in Political Science,” Libby Jenke and Nicolette Sullivan explain what eye tracking allows researchers to measure and how these measures are relevant to political science questions.
what are large language models actually doing?
i read the 2025 textbook "Foundations of Large Language Models" by tong xiao and jingbo zhu and for the first time, i truly understood how they work.
here’s everything you need to know about llms in 3 minutes↓
🚨 New paper in @ScienceAdvances
Can changing how we argue about politics online improve the quality of replies we get?
@THeideJorgensen, @a_rasmussen, and I use an LLM to manipulate counter-arguments to see how people respond to different approaches to arguments.
Thread 🧵1/n
This research advances a mechanistic reward learning account of social learning strategies. Through experiments & simulations, it shows how people learn to learn from others, dynamically shaping the processes involved in cultural evolution. @DSchultnernature.com/articles/s4156…
🚨New paper in @TrendsCognSci 🚨
Why do some ideas spread widely, while others fail to catch on?
@jayvanbavel and I review the “psychology of virality,” or the psychological and structural factors that shape information spread online and offline.
Thread 🧵(1/n)
Can large language models (LLMs) fairly annotate data on contentious topics?
Our new paper dives into this question—looking at whether LLM-generated labels reflect diverse viewpoints or skew toward majority perspectives. The results are surprisingly nuanced. 🧵
An AI model (Llama 3.1 70B) fine-tuned on the results of 60,000 people in psychology experiments shows some real promise in using LLMs for studying human behavior.
It predicts actual human behavior in held-out data & it generalizes to out-of-distribution tasks and experiments.
LLMs can effectively depolarize social media content while maintaining textual coherence, finds Santos et al., using a between-subjects experiment doi.org/10.1145/371786…
a new article forthcoming in Political Psychology: osf.io/rhf4q!
we argue that studies of belief change have an "identifiability problem," much like the APC problem: the composition of change---who changed or how much they changed---is observationally confounded.
⁉️In survey experiments, should you ask covariates before the treatment?
➡️@asdurso@TabithaBonilla & G.Bogdanowicz study the effects of placing sensitive items in different parts of the survey flow and offer guidance on optimal question order cambridge.org/core/journals/…#FirstView
🧵 NEW PAPER - "Quantifying Narrative Similarity Across Languages" is live at SMR. We combine NLP w pairwise LLM evals to track ideas across media ecosystems and languages. We also figured out a way to eval unsupervised probs on widely understood supervised performance metrics.
Interesting paper: 161 researchers in 73 research teams used the same data and hypothesis (immigration reduces support for social policies among the public), but arrived at different results and conclusions.
Paper in PNAS
Want to add an LLM chatbot to your Qualtrics surveys? Here's a step-by-step guide showing exactly how to do this with AWS Bedrock joshuakalla.github.io/llm_persuasion/
Excited to share our new paper, examining cross-cultural variability within the theory of planned behavior, a large meta-meta-analysis with data from 956 studies from 54 countries
How to improve conceptual clarity in psychology?
Excited to share a new preprint with Rui Mata, discussing approaches based on large language models as possible solutions.
Preprint: osf.io/preprints/psya…
522 Followers 3K FollowingMPhil in Government and Public Administration (International Relations) @CUHKOfficial; BSocSc (1st Hons) in G11N & Devt, @HKBaptistU @BNBU_GBA
138 Followers 336 FollowingPhD student @CSatUSC. Computational Social Science, AI for Social Science, Social Networks. Ex @MSFTResearch Asia, @Tsinghua_Uni. Ballerina.
329 Followers 653 FollowingPh.D. student @UM_CommStudies (she/her/她)
Alumni @Tsinghua_Uni
I study science communication & computational social science.
#WomenAlsoKnowStuff
224 Followers 353 FollowingPhD student in Media, Technology, and Society @NorthwesternU; alum @COMatBU @hkust. Being kind, independent, brave, and free ~🇨🇳🇭🇰🇺🇸📷🏃♀️
3K Followers 1K FollowingCommunication Prof, FGV Law Visiting Prof, New America, China/Global South tech policy, Digital Sovereignty in BRICS (Cambridge Univ Press) https://t.co/NBstfsFlxU
972 Followers 837 Followingphd candidate @oiioxford @uniofoxford | research scientist @AISecurityInst | AI, social data science, persuasion with language models
125 Followers 253 FollowingPhD student in political science. Main areas of study are political communication and authoritarian politics, with a focus on Chinese politics.
3K Followers 917 FollowingAssistant Professor in Computational Social Science at ILLC @UvA_amsterdam |
Studying the intersection of AI, social media, and politics
507 Followers 388 Following@MIT // researching fairness, equity, & pluralistic alignment in LLMs
previously @medialab, @Mila_Quebec / @mcgillu
i like language and frisbees and sunsets
48K Followers 0 FollowingAutomatically tweets new posts from https://t.co/A8uFi473gj
Please respond in the comment section of the blog.
Old posts spool at https://t.co/HLEEe8oMCd
6K Followers 1K FollowingKellogg Chair of Technology at Kellogg, Founding director, Center for Science of Science and Innovation, Northwestern University
520 Followers 937 FollowingAnthropologist @hkuniversity, award winning author on #religion, #spirituality, society and politics in #China and #Asia @hkihss @hkusociology @asiarhk
3K Followers 983 FollowingRefugee || Professor at University of Pennsylvania @Penn_CSNBD @PennMBDS || Studying dark side of human behavior || 🇲🇩 born — 🇩🇪 grown — 🇺🇸 based
976 Followers 681 FollowingInternet as a governance lab
Computational institutions/commons/community/cogsci
Science towards Nescience
Prof.
(h/t for punk Lin: http://t.co/BfLLbON6wK)
1K Followers 573 FollowingEvolution of search and cognition, language, mind, and society. Network science and NLP. Professor University of Warwick. Darwin's greenhouse.
2K Followers 46 FollowingThe Hong Kong Institute for the Humanities and Social Sciences at HKU promotes multi-disciplinary research and teaching in the humanities and social sciences
10K Followers 789 FollowingPolitical Science Research and Methods: The journal of #EPSA (European Political Science Association), edited by John Griffin (@griffin_j_d), published by CUP
4K Followers 3K FollowingPioneers Chair in Telecom @psubellisario Researching/writing about all things broadband Author of: Farm Fresh Broadband https://t.co/xD6sUcyF0q 🏳️🌈🇨🇦
214 Followers 247 FollowingPhD candidate in political science @UCBerkeley MPhil in International Relations @Politics_Oxford Bachelor of Social Sciences @HKUniversity
842 Followers 67 FollowingThe SSPP enables researchers to collect and contribute to forecasts of academic studies.
Tweets by @UCBITSS @evavivalt @socscipredict.bsky.social
No recent Favorites. New Favorites will appear here.